Semantics for robotic mapping, perception and interaction: A survey
For robots to navigate and interact more richly with the world around them, they will likely
require a deeper understanding of the world in which they operate. In robotics and related …
require a deeper understanding of the world in which they operate. In robotics and related …
Affordances in robotic tasks--a survey
Affordances are key attributes of what must be perceived by an autonomous robotic agent in
order to effectively interact with novel objects. Historically, the concept derives from the …
order to effectively interact with novel objects. Historically, the concept derives from the …
Self-assessment of grasp affordance transfer
Reasoning about object grasp affordances allows an autonomous agent to estimate the
most suitable grasp to execute a task. While current approaches for estimating grasp …
most suitable grasp to execute a task. While current approaches for estimating grasp …
Predicting pushing action effects on spatial object relations by learning internal prediction models
Understanding the effects of actions is essential for planning and executing robot tasks. By
imagining possible action consequences, a robot can choose specific action parameters to …
imagining possible action consequences, a robot can choose specific action parameters to …
Representing spatial object relations as parametric polar distribution for scene manipulation based on verbal commands
Understanding spatial relations is a key element for natural human-robot interaction.
Especially, a robot must be able to manipulate a given scene according to a human verbal …
Especially, a robot must be able to manipulate a given scene according to a human verbal …
Humans predict action using grammar-like structures
F Wörgötter, F Ziaeetabar, S Pfeiffer, O Kaya… - Scientific reports, 2020 - nature.com
Efficient action prediction is of central importance for the fluent workflow between humans
and equally so for human-robot interaction. To achieve prediction, actions can be …
and equally so for human-robot interaction. To achieve prediction, actions can be …
Building plannable representations with mixed reality
We propose Action-Oriented Semantic Maps (AOSMs), a representation that enables a robot
to acquire object manipulation behaviors and semantic information about the environment …
to acquire object manipulation behaviors and semantic information about the environment …
Reconstructing spatial aspects of motion by image-to-path deep neural networks
The choice of an appropriate representation is important when reconstructing motion from
images. In this letter we propose a new type of deep neural network (DNN) that maps …
images. In this letter we propose a new type of deep neural network (DNN) that maps …
Fine-grained action plausibility rating
T Lueddecke, F Woergoetter - Robotics and Autonomous Systems, 2020 - Elsevier
An essential capability of humans is the effortless identification of useful tasks based on
visual cues in everyday situations. Objects and their surroundings are integrated and …
visual cues in everyday situations. Objects and their surroundings are integrated and …
Compliance-based affordance templates for remote mobile manipulation
CM Elliott - 2020 - repositories.lib.utexas.edu
This thesis details the implementation of Affordance Templates with a compliance controller
to pseudo-autonomously perform complex contact tasks in industrial environments. Multiple …
to pseudo-autonomously perform complex contact tasks in industrial environments. Multiple …